public static function __cutAll($sentence, $options = array())
{
$defaults = array('mode' => 'default');
$options = array_merge($defaults, $options);
$words = array();
$DAG = self::getDAG($sentence);
$old_j = -1;
foreach ($DAG as $k => $L) {
if (count($L) == 1 && $k > $old_j) {
$word = mb_substr($sentence, $k, $L[0] - $k + 1, 'UTF-8');
array_push($words, $word);
$old_j = $L[0];
} else {
foreach ($L as $j) {
if ($j > $k) {
$word = mb_substr($sentence, $k, $j - $k + 1, 'UTF-8');
array_push($words, $word);
$old_j = $j;
}
}
}
}
return $words;
}
/** * Static method cut * * @param string $sentence # input sentence * @param boolean $cut_all # cut_all or not * @param array $options # other options * * @return array $seg_list */ public static function cut($sentence, $cut_all = false, $options = array()) { $defaults = array('mode' => 'default'); $options = array_merge($defaults, $options); $seg_list = array(); $re_han_pattern = '([\\x{4E00}-\\x{9FA5}]+)'; $re_skip_pattern = '([a-zA-Z0-9+#\\n]+)'; preg_match_all('/(' . $re_han_pattern . '|' . $re_skip_pattern . ')/u', $sentence, $matches, PREG_PATTERN_ORDER); $blocks = $matches[0]; foreach ($blocks as $blk) { if (preg_match('/' . $re_han_pattern . '/u', $blk)) { if ($cut_all) { $words = Jieba::__cutAll($blk); } else { $words = Jieba::__cutDAG($blk); } foreach ($words as $word) { array_push($seg_list, $word); } } else { array_push($seg_list, $blk); } // end else (preg_match('/'.$re_han_pattern.'/u', $blk)) } // end foreach ($blocks as $blk) return $seg_list; }